output
20052026
most citedDistract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition

276 citations

Showing 2023 · cs.CVShow all

6 papers · 2 filters

cs.CV2023★ 6 cited

CAMEL2: Enhancing weakly supervised learning for histopathology images by incorporating the significance ratio

Gang Xu, Shuhao Wang, Lingyu Zhao +12

Histopathology image analysis plays a crucial role in cancer diagnosis. However, training a clinically applicable segmentation algorithm requires pathologists to engage in labour-i…

cs.CV2023★ 12 cited

Class-Specific Distribution Alignment for Semi-Supervised Medical Image Classification

Zhongzheng Huang, Jiawei Wu, Tao Wang +2

Despite the success of deep neural networks in medical image classification, the problem remains challenging as data annotation is time-consuming, and the class distribution is imb…

cs.CV2023★ 8 cited

Semi-Supervised Medical Image Segmentation with Co-Distribution Alignment

Tao Wang, Zhongzheng Huang, Jiawei Wu +2

Medical image segmentation has made significant progress when a large amount of labeled data are available. However, annotating medical image segmentation datasets is expensive due…

cs.CV2023

Spatio-Temporal Context Modeling for Road Obstacle Detection

Xiuen Wu, Tao Wang, Lingyu Liang +2

Road obstacle detection is an important problem for vehicle driving safety. In this paper, we aim to obtain robust road obstacle detection based on spatio-temporal context modeling…

cs.CV2023★ 1 cited

A Multi-Scale Framework for Out-of-Distribution Detection in Dermoscopic Images

Zhongzheng Huang, Tao Wang, Yuanzheng Cai +1

The automatic detection of skin diseases via dermoscopic images can improve the efficiency in diagnosis and help doctors make more accurate judgments. However, conventional skin di…

cs.CV2023★ 2 cited

Robust Remote Sensing Scene Classification with Multi-View Voting and Entropy Ranking

Jinyang Wang, Tao Wang, Min Gan +1

Deep convolutional neural networks have been widely used in scene classification of remotely sensed images. In this work, we propose a robust learning method for the task that is s…